Search tools
Tool
S

Claude Code

Anthropic's agentic coding tool for the terminal, IDE, desktop and web.

Official site: claude.com Free tier: No Open source: No Platforms: CLI, IDE, Desktop, Web
Last verified: Oct 15, 2026 Last tested: Not yet, hands-on test pending
⚠ Preliminary, based on public research, hands-on test pending. These scores come from a desk review of public sources (official pricing pages, docs, changelogs), linked on each tool page. Rex hasn't run the hands-on tests yet, so tiers shown are projected. Under our rubric, a tool's official tier is capped at B until it's tested.

What looks good

  • Works directly in your existing repo from the terminal or IDE
  • Strong builder-fit: CLI, MCP support, hooks and scripting
  • Included in the standard Claude subscription, no separate product to buy

Watch-outs

  • No free tier for Claude Code
  • Usage shares the same 5-hour limits as Claude chat; heavy use pushes you to $100-200 Max plans

From public sources below, not from our own hands-on testing (yet).

Scores

Rank #1 · projected tier S · official tier B (untested cap) · ⚠ Preliminary

The terminal-native agent many builders reach for first; maxed builder-fit (CLI, MCP, hooks). Heavy use pushes you to the $100-200 Max plans.

Output quality on the job test 31/35
Speed & friction 13/15
Value / price 11/15
Control & ownership 8/10
Momentum & community 10/10
Reliability & trust 8/10
Builder-fit 5/5
Total86/100

Pricing as found Oct 15, 2026

PlanPriceNotes
Pro$20/mo ($17/mo yearly)Claude Code included; shares limits with Claude chat
Max 5x$100/mo5x Pro usage per session
Max 20x$200/mo20x Pro usage per session
APIPay per tokenVia Anthropic API key

Prices in USD, excluding tax. Vendors change pricing often; check the official page before buying.

Patch history

buff

Claude Code 2.1.304: guided auto mode setup and a usage warning on resume

A new /auto-mode-setup command reads your project and recent sessions to teach auto mode about your environment. On Pro and Max plans, Claude Code now warns you when resuming an old conversation would eat a noticeable share of your 5-hour usage limit, and offers to start fresh instead. Also fixes rm -r on mounted drives skipping the safety prompt. Source

buff

Claude Code 2.1.302: pick the auto mode classifier model

A new CLAUDE_CODE_AUTO_MODE_MODEL setting chooses which model the client-side auto mode classifier uses, and /config gets a row to turn idle compaction off or back on. The release also warns that standalone Claude Design (claude.ai/design) closes by December 14, 2026. Source

buff

Claude Code compacts idle long sessions before the cache expires

In the terminal, a 200K+ token conversation left idle for about 54 minutes is now compacted before its one-hour prompt cache expires, so the next message doesn't reprocess everything. Tune it with CLAUDE_CODE_IDLE_COMPACT_MIN_TOKENS or turn it off with "idleCompaction": false. Source

Alternatives

A
OpenAI Codex
84/100 · projected
A
Cursor
80/100 · projected
A
GitHub Copilot
79/100 · projected
A
Cline
78/100 · projected

Sources

  1. Claude pricing (claude.com)
  2. Claude Help: Claude Code with Pro or Max (support.claude.com)
  3. Claude Code product page (claude.com)

Accessed Oct 15, 2026. Spot an error? Request a correction.